307 results about "Manufacturing quality" patented technology

The invention relates to the technical field of twinborn model simulation, and discloses a twinborn model simulation method and system for hot working of large forgings. The method comprises the following steps: collecting and preprocessing process parameters, quality data and environment information in a multi-source manner, and obtaining hot working characteristic data; performing correlation analysis to construct a process knowledge graph; calculating the distribution of a temperature field, a stress field and an organization field by using a self-sensing multi-field coupling var value neural network; comparing and analyzing to obtain deviation data and correction parameters; adjusting a network parameter optimization prediction result; and executing multi-objective optimization calculation, and generating a whole-process technological parameter and a control instruction. According to the method, full-process multi-physics field coupling calculation from smelting, casting, forging and pressing to heat treatment can be achieved, model parameters are dynamically adjusted according to real-time production data, the optimal process scheme is generated, and therefore the manufacturing quality and efficiency of large forgings are improved.

The invention discloses an aluminum alloy surface defect detection method and system using deep learning, and relates to the related field of detection performed in combination with deep learning, and the method comprises the following steps: carrying out image acquisition on an aluminum alloy finished product, constructing a surface image data set to extract multi-scale surface features, and constructing a feature enhanced image set to carry out defect detection, and a defect detection result is obtained to dynamically optimize aluminum alloy production process parameters, and a process adjustment instruction is generated and fed back to a production system. The technical problems that traditional detection mostly depends on manual visual inspection or a machine vision system based on rules, imaging distortion, small defect missing detection and process adjustment are caused are solved, and the technical effects that deep learning is conducted through the double-branch network, the defect detection efficiency and the production yield are improved, and control over the aluminum alloy manufacturing quality is met are achieved.

The invention provides an abnormity early warning method and system used in a fan manufacturing process. The abnormity early warning method comprises the steps that a multi-source process data stream composed of part forming process data, structure assembling process data and performance testing process data in the fan manufacturing process is acquired; performing process feature analysis processing on the multi-source process data stream to obtain a time sequence evolution feature process coupling feature; performing combined anomaly identification processing on the time sequence evolution features and the process coupling features through a pre-deployed manufacturing anomaly diagnosis model to generate a process anomaly identification result; based on the front-back sequence relation of all the procedures in the fan manufacturing process and the abnormal probability value and the possibility level in the procedure abnormal identification result, the abnormal target procedure node and the associated procedure range of the abnormal influence are positioned; and generating an early warning instruction according to the target process node and the associated process range, and pushing the early warning instruction to a manufacturing execution system. Abnormity real-time monitoring and early warning in the fan manufacturing process are achieved, and the fan manufacturing quality and production efficiency are improved.

The invention discloses a wind power generation ring forging three-dimensional design and quality management system based on 5G communication, and belongs to the technical field of wind power equipment manufacturing. The system comprises a modeling module used for constructing a parameterized three-dimensional design model and outputting design parameters used for quality evaluation and defect identification; the process data acquisition module acquires process data such as temperature, pressure and vibration of the key structure area in real time; the defect identification module fuses the image and the signal data, and outputs defect types, positions and sensitivity influences thereof; the quality evaluation module performs quantitative scoring on the product quality based on the scoring function and the disturbance response parameters; the feedback regulation and control module identifies the dominant deviation and generates a regulation and control instruction when the score is abnormal; and the 5G communication module realizes high-speed data interaction between the modules. The method realizes closed-loop control of design, manufacturing, detection and evaluation, improves the manufacturing quality and efficiency of ring forgings, and is suitable for manufacturing scenes of large-size and high-reliability wind power structural members.

The invention discloses a quality detection method and system for vehicle safety belt production and a storage medium, and relates to the field of manufacturing quality control of automobile passive safety parts. The method aims at solving the problems that an existing detection means is weak in tiny defect recognition capacity, insufficient in defect evolution modeling and lack of intelligent feedback regulation and control. According to the method, multiple detection means such as medium-wave infrared thermal imaging, laser confocal microscopy, structured light three-dimensional reconstruction and capacitance sensing are fused, and multi-mode defect sensing of key parts such as a braid, an insertion area and an adhesive layer is achieved; deducing a defect evolution process and generating a high-credibility pseudo label by constructing a thermal-stress-rheology coupling finite element model; the graph neural network and the AI model are combined to complete defect type identification, risk quantification and grading, and automatic optimization of process parameters and production line control response are realized based on the quality grade, so that the detection precision, the response efficiency and the product yield are remarkably improved.

The invention relates to the technical field of artificial intelligence, and discloses a motor manufacturing quality intelligent detection system which comprises a sensor data acquisition module, a data processing module, an artificial intelligence analysis module, a decision feedback module and a report generation module. Aiming at electromagnetic interference and mechanical noise generated by multiple processes, a self-adaptive signal filtering mechanism is established, transient interference components of data collected by a sensor can be reduced in real time, the extraction integrity of key characteristic parameters such as vibration and temperature is ensured, the misjudgment risk caused by signal distortion is reduced, the problem that the omission ratio is too high in traditional detection is solved, and the detection accuracy is improved. And a dynamic association rule base is constructed, so that the system can capture early fault symptoms which cannot be recognized by a traditional single-dimensional model, prediction blind areas caused by multi-field data splitting are reduced, and the product life prediction precision is improved.

The invention belongs to the technical field of intelligent manufacturing, and particularly relates to a manufacturing quality prediction method and system based on a multi-mode sequential network and application, and the method comprises the steps: carrying out the preprocessing of the sequential data of a process manufacturing production line, obtaining a sample set, and carrying out the sequential division into a training set, a verification set and a test set; on the basis of the sample set, key features are enhanced through a frequency domain enhanced channel attention mechanism, a multi-period mode of a time sequence dependence and period sensing module is captured in combination with a multi-layer expansion convolutional network structure, and a multi-mode time sequence network model is constructed; and sequentially carrying out training set training, verification set parameter adjustment optimization and test set performance verification on the multi-modal sequential network model, and outputting a prediction result. According to the method, the deep dynamic association among the multivariable time series data can be mined, the accuracy and robustness of manufacturing quality prediction are improved, and an efficient and reliable technical scheme and an implementation path are provided for process industry quality control and intelligent optimization.

The invention discloses a manufacturing quality analysis system and method based on a large model Agent and MCP, and mainly relates to the field of intelligent manufacturing and artificial intelligence application. Comprising the following steps: S1, initializing a setting stage layer; s2, a data input stage layer; s3, a data processing stage layer; s4, an intelligent analysis stage; and S5, a result output stage. The system further comprises a large model agent Agent module. An agent Agent selection module; a data acquisition module; a data preprocessing module; and an analysis and report generation module. The method has the beneficial effects that through combined application between the large model Agent and the large model MCP, the process quality data processing analysis efficiency can be improved by more than 30%, and the quality analysis and decision suggestion output of the six-sigma black band level is provided through the AI; the limitations of an existing system in the aspects of strong manual dependence, lagging analysis timeliness, lack of quality talents and the like are solved.

The invention provides an intelligent manufacturing quality management method, system and equipment based on edge cloud collaboration, and belongs to the technical field of intelligent manufacturing. The method comprises the following steps: collecting multi-source heterogeneous data in real time through an edge computing node deployed in a production field; performing space-time alignment and feature extraction on the multi-source heterogeneous data to generate a standardized quality feature vector; inputting the quality feature vector into a pre-trained quality prediction model, outputting a real-time quality evaluation result and an abnormal probability, and determining a quality abnormal event; when a quality abnormal event is detected, a process parameter optimization scheme is generated based on simulation of a digital twin model, and operation parameters of production equipment are dynamically adjusted through an edge controller; and encrypting and storing the quality abnormal event, the adjusted process parameters and related production batch information to a block chain, and generating a non-tampering quality tracing chain. According to the invention, real-time monitoring and accurate prediction of production quality, rapid response of quality abnormity and dynamic adjustment of process parameters are realized.

The invention relates to a manufacturing process quality tracing and root cause analysis system based on a data graph, and belongs to the technical field of manufacturing process quality control. The system performs cleaning, duplicate removal and standardization processing on multi-source heterogeneous data in the whole manufacturing process through a data processing module to generate structured data; the data graph construction module fuses the manufacturing domain knowledge ontology, constructs a manufacturing process digital twin semantic model and a multi-dimensional manufacturing data graph, introduces a dynamic association weight updating mechanism and mines node potential implicit association; the quality tracing module positions map nodes based on query semantic vectors, and reconstructs an entity state change track by using a digital twin semantic model to generate a tracing link; and the root cause analysis module screens candidate abnormal factors, locates a root cause in combination with dynamic weight and multi-scene simulation verification, and generates a quality optimization scheme. According to the invention, full-link accurate tracing and root cause efficient positioning of the manufacturing process quality are realized, and the intelligence and refinement level of manufacturing quality management and control is improved.

The invention provides an intelligent optimization method and system for metal additive manufacturing process parameters based on Bayesian optimization, and the method comprises the steps: testing the performance parameters of samples prepared under different additive manufacturing process parameters, and constructing a data set; based on the data set, training a single performance prediction model through a Gaussian regression algorithm, performing weighting processing on a plurality of performance parameters to obtain comprehensive performance, and training a comprehensive performance prediction model; performing Bayesian optimization by taking the comprehensive performance prediction model as an agent model; determining recommended process parameters according to a Bayesian optimization result, and predicting a predicted value of the sample under the recommended process parameters through a single performance prediction model; and based on the error between the measured value and the predicted value of the prepared sample, updating the data set and circularly carrying out model training and Bayesian optimization until the process parameters meeting the requirements are obtained. According to the method, a complex additive manufacturing process parameter space can be efficiently explored, and a plurality of conflicting additive manufacturing quality indexes are collaboratively optimized.

The invention provides a hot rolled steel strip surface defect detection method based on target detection, and aims to solve the problems of difficulty in multi-scale small target recognition, insufficient feature fusion and complex background interference in hot rolled steel strip surface defect detection. Extracting multi-scale defect features by using wavelet convolution through decomposition, convolution and reconstruction processes; multi-scale features are adaptively fused based on channels and space attention through a dynamic feature fusion module (DFF); a dynamic hyperbolic tangent function (DyT) is used to replace a normalization layer to dynamically adjust the input range and compress extreme values to reduce the amount of calculation. The method has the effects of high detection average precision (mAP), low missing report rate and remarkably reduced calculation complexity, effectively improves the efficiency and reliability of identifying the surface defects of the hot rolled steel strip in a complex industrial environment, and is suitable for intelligent steel manufacturing quality control.

The invention provides a railway vehicle production and manufacturing digital twin system and method. A data acquisition module is used for acquiring railway vehicle production and manufacturing quality data; the data processing module is used for classifying the railway vehicle production and manufacturing quality data to obtain classified quality data; the data interface determination module is used for determining an interface form between the classified quality data and the railway vehicle production and manufacturing digital twin platform; and the twinborn model establishing module is used for designing the digital twinborn model on the railway vehicle production and manufacturing digital twinborn platform, and driving the size change of the digital twinborn model according to the classified quality data, so that the digital twinborn model is kept consistent with the classified quality data. The digital twinning platform can generate the twinning vehicle body with the current vehicle production and manufacturing data as the size, the railway vehicle production and manufacturing quality data can be checked conveniently, and important decision support is provided for production and manufacturing.

The invention discloses a metal structural member manufacturing quality online monitoring system, and particularly relates to the technical field of quality monitoring, and the system comprises an on-site perception and edge processing unit, a cloud digital twin unit, a cloud decision and optimization unit and a closed-loop control unit. The field unit collects multi-modal physical signals in real time and carries out preprocessing and defect preliminary classification based on a lightweight AI model; the digital twin unit drives a high-fidelity virtual model based on field data, and simulates a defect evolution and repair strategy through finite element simulation; the decision-making unit fuses classification and simulation results to generate an executable repair instruction, and performs collaborative optimization on an AI model and a simulation algorithm based on feedback data; the closed-loop unit controls instruction issuing and field execution, and real-time regulation and control and system self-optimization of the repair process are achieved. According to the system, full-process online monitoring, intelligent diagnosis and self-adaptive repairing of the manufacturing process are achieved, and the production quality and efficiency of the metal structural part are remarkably improved.

The invention discloses a PCB manufacturing quality detection method, system and device based on a dynamic threshold value and a medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining a plurality of split subspaces; acquiring detection data, acquiring a historical compensation coefficient, and acquiring a first real-time compensation coefficient; acquiring a data sequence of each fragment subspace according to detection data of each fragment subspace at a plurality of continuous detection time points, acquiring a trend index of each fragment subspace according to the data sequence of each fragment subspace, and acquiring a second real-time compensation coefficient according to the trend index of each fragment subspace; and obtaining a standard threshold value, obtaining a dynamic threshold value according to the standard threshold value, the first real-time compensation coefficient and the second real-time compensation coefficient, and obtaining a quality detection result according to the detection data of each fragment subspace at the current detection time point and the dynamic threshold value. The method has the advantages of dynamic threshold, accurate positioning and good detection effect.

The invention relates to the technical field of switch cabinet production, and particularly discloses a switch cabinet body plate laser cutting method, device and equipment and a medium, and the method comprises the steps that a three-dimensional design model and a two-dimensional expansion drawing of a target switch cabinet body are obtained; identifying the three-dimensional design model and extracting machining features about the cutting process; predicting the cutting deformation of the cabinet plate; according to the predicted cutting deformation, the offset of the machining features on the two-dimensional expansion graph is deduced reversely; generating a two-dimensional cutting map containing the compensated processing features; a cutting deviation factor is analyzed based on the two-dimensional cutting graph, a cutting sequence and a cutting forming path are optimized based on the cutting deviation factor, and a cutting strategy is generated; according to the method, a reliable reverse calculation mechanism is provided to compensate dimensional deviation caused by a forming process, accurate association of feature positions is ensured, and the laser cutting precision and the overall manufacturing quality of the switch cabinet body plate are remarkably improved.

The invention discloses an industrial surface defect anomaly detection method based on edge guidance. The method comprises the following steps: 1) performing positive sample collection on industrial parts produced by a factory to obtain training samples; 2) performing data preprocessing on the acquired positive sample image, randomly adding Berlin noise on the image, generating a synthetic negative sample, and using a sample pair as input of model training; 3) performing model training on the acquired sample by using E2TS-Seg to accurately segment a pseudo abnormal region of the specified industrial product; and 4) carrying out anomaly detection screening on a to-be-detected industrial product by using the trained model. Compared with traditional manual detection, the method has remarkable advantages in the aspects of detection precision, efficiency and adaptability, can meet the requirements of an industrial production line for real-time detection of submillimeter defects, and provides reliable technical support for intelligent manufacturing quality control.

The invention discloses an additive manufacturing powder bed preheating system and method based on hot air-partition radiation synergy. The additive manufacturing powder bed preheating system comprises a preheating outer box, a powder bed, a hot air circulating system, a partition radiation heating system and a layering synergy controller. The method has the beneficial effects that an upper-layer steady-state optimization and lower-layer dynamic compensation framework is adopted, wherein the upper layer aims at energy efficiency and temperature uniformity, and the temperature and the air speed of a hot air inlet are optimized; and the lower layer is based on real-time temperature feedback, the partition radiation power is adjusted through a feedback + feedforward decoupling algorithm, local temperature disturbance is compensated, hot air rapidity and partition radiation accuracy are fused, the problems of response lag, space coupling and laser preheating cooperation deficiency are solved, rapid, uniform and dynamic regulation and control of the temperature field of the powder bed are achieved, the additive manufacturing quality is improved, and the production efficiency is improved. The method is suitable for high-precision manufacturing of various high polymer materials.

The invention discloses an efficient welding method for an exhaust silencer of a motorcycle. According to the invention, breakthrough improvement of manufacturing quality and efficiency is realized through multi-dimensional technical innovation. A high-frequency electromagnetic field resonance stress relief technology is creatively introduced, the metal crystallization behavior is intervened in real time in the welding process, and the thermodynamic equilibrium state of traditional welding is fundamentally reconstructed. Electromagnetic energy directly acts on molten metal in a microscopic particle vibration mode, lattice defects are promoted to be spontaneously repaired in the liquid stage, the deformation cracking risk caused by thermal stress accumulation in a traditional technology is avoided, and microstructure optimization is more synchronously completed. According to the dynamic energy field regulation and control means, the welding strength and toughness of the complex curved surface structure of the silencer are synergistically enhanced, a uniform and compact fine grain structure is formed in a welding seam area, the anti-fatigue performance of a product under the impact of high-temperature tail gas is remarkably improved, meanwhile, the necessary annealing procedure after traditional welding is integrated into in-situ treatment, and the production efficiency is improved. And the production period is greatly shortened.

The embodiment of the invention discloses a personalized ear mold integrated manufacturing method based on multi-material digital light processing, and relates to the technical field of additive manufacturing. The method comprises the following steps: acquiring a personalized ear mold three-dimensional numerical model of a specific patient; adding a static load based on the dead weight of the hearing aid and a dynamic load based on the periodic force of the chewing motion to the numerical model, and performing dynamic stress analysis on the numerical model based on the added loads; based on a stress analysis result, dividing material areas with different hardness in the numerical model, including a rigid supporting area, a flexible sealing area and a transition area; according to the stress gradient line, the volume fraction of the rigid material and the volume fraction of the flexible material used for DLP three-dimensional printing at all positions in the transition area are determined; and according to the volume fraction and the printing energy density of the rigid supporting area and the printing energy density of the flexible sealing area, the printing energy density of all the positions in the transition area is determined. According to the embodiment, the manufacturing quality and efficiency of the ear mold can be improved.

The invention discloses a large metal thin-wall component manufacturing method based on stress distribution state management, which comprises the following steps of: aiming at the configuration of a large metal thin-wall component to be manufactured, constructing a manufacturing process combining reverse modeling analysis and forward process design; the reverse modeling analysis starts from the working step at the tail end of the manufacturing process, the stress distribution state between the working steps serves as a transmission and control element, and in the direction from the tail end to the front end, each working step proposes the final stress distribution state meeting the most simplified requirement of the manufacturing scheme of the working step for the previous working step; and based on the result of the reverse modeling analysis, on the basis of the final stress state determined by the previous step, the tool and the forming process of each step are determined, so that the final stress distribution state of the component manufactured by the step meets the requirements of the next step. The problems that the forming precision of a large metal thin-wall component welding component is poor, the precision coordination consistency of all procedures is poor, and the component manufacturing quality is difficult to guarantee are solved.

The utility model relates to the technical field of semiconductors, in particular to a wafer loading and detecting integrated device, which comprises a bottom frame and a back plate, and is characterized in that a mounting cavity is arranged in the bottom frame, and a box reading platform deck for bearing and identifying a wafer box and a detecting frame mechanism for detecting the wafer box and a wafer are arranged in the mounting cavity; the detection frame mechanism is arranged on the periphery of the box reading carrying table in a covering mode, and the detection frame mechanism is driven by the lifting assembly to ascend and descend on the front end face of the back plate. According to the utility model, the whole structure is simple, and the bearing function of the wafer box and the quality control function of the wafer carrying result after the cover of the wafer box is opened are integrated; the equipment size is integrally reduced, the wafer detection requirements in the wafer storage, wafer taking, cover opening and cover closing processes are considered, multiple detection operation procedures in the wafer manufacturing and machining processes are reduced, and subsequent larger manufacturing quality problems caused by pollution, bending and storage protrusion of the wafer are reduced.

The invention discloses a model training method, an anomaly detection method, electronic equipment and a storage medium, relates to the technical field of manufacturing quality inspection, and is used for improving the accuracy of anomaly detection in industrial quality inspection. The model training method comprises the following steps: acquiring target modal data of a target object; determining abnormal features of the target object based on the target modal data of the target object and a first detection model; training a to-be-trained second detection model based on the abnormal features of the target object and the target modal data of the target object; the second detection model is used for identifying abnormal information existing in the target object based on the target modal data of the target object.

The invention discloses an anomaly detection method and system based on multi-modal monitoring data antagonism fusion, and belongs to the technical field of additive manufacturing quality monitoring. The method comprises the following steps: synchronously acquiring image, vibration and temperature data through multiple sensors; mapping the multi-modal data to a unified low-dimensional space by using a generative adversarial network to carry out adversarial fusion, and generating fusion features with strong discrimination; and the fusion features are classified based on a support vector machine, and anomaly detection in the additive manufacturing process is achieved. The system comprises an acquisition module, a fusion module and a detection module. According to the method, the problems that single sensor detection is large in limitation and multi-modal data fusion is difficult are effectively solved, the accuracy, robustness and real-time performance of anomaly detection are remarkably improved, and the method is suitable for intelligent monitoring and quality control in the industrial-grade additive manufacturing process.

The invention provides a manufacturing process quality improvement method based on multi-source data perception in order to solve the problem that an existing method can only achieve quality prediction and cannot achieve quality improvement. The method comprises the following steps: sensing multi-source heterogeneous data during manufacturing, and extracting knowledge from the multi-source heterogeneous data to construct a manufacturing process technology knowledge graph; a Resnet-LSTM quality prediction model is constructed and trained to predict defect types, key factors influencing defects are determined in combination with a manufacturing process technology knowledge graph, a multi-source sensor is deployed based on the key factors, multi-source sensor data influencing the defects can be sensed more accurately, an attention mechanism is introduced to perform weighted summation on the multi-source sensor data, and the defect detection accuracy is improved. The method comprises the following steps of: inputting the data into a trained CNN-ABILSTM quality improvement model to obtain a more accurate and credible quality prediction result, generating a process adjustment scheme capable of improving the manufacturing quality according to the quality prediction result in combination with a manufacturing process process knowledge graph, and improving the quality control and problem traceability during the manufacturing period.

The invention relates to caterpillar track section feeding equipment and a working method thereof, and is characterized in that the caterpillar track section feeding equipment comprises a rack, a material box capable of moving in and out of the rack, and a feeding manipulator device which is arranged on the rack and used for grabbing caterpillar track sections in the material box, adjusting the posture of the caterpillar track sections and then putting the caterpillar track sections into a transfer clamp device; the rack is further provided with a caterpillar track section positioning and conveying device used for conveying caterpillar track sections, and the outlet end of the caterpillar track section positioning and conveying device is provided with a material placing mechanical arm device capable of transferring the caterpillar track sections on the caterpillar track section positioning and conveying device into the feeding and positioning clamp device. According to the caterpillar track section feeding equipment and the working method thereof, the feeding problem of traditional mechanical equipment is solved, the labor intensity of workers is greatly reduced, the manufacturing quality and the production efficiency of caterpillar track sections are remarkably improved, and reliable guarantee is provided for improvement of the machining precision of subsequent procedures.

The invention discloses a circumferential contour prediction method based on cutting force and deformation field space-time correlation, and relates to the field of aerospace, and the method comprises the following steps: 1, carrying out the spatial discretization of a circumferential contour region of a target workpiece; step 2, establishing a lightweight structure stiffness matrix; 3, constructing an elastic mechanism model and solving delta-F mapping; 4, introducing the time sequence correlation of the cutting load into the elastic mechanism model; step 5, constructing a Boolean relationship between the tool path and the workpiece envelope; step 6, fusing actual measurement process signals, and performing state correction; step 7, iterating the elastic model again by using the corrected load; and step 8, reconstructing full-field deformation based on spatial correlation. According to the method, online prediction of the station-level circumferential deformation field is achieved, the method can be used in the multi-procedure machining process, deformation in-situ compensation of the procedure is achieved, a clamping positioning strategy of the next procedure is output, and the manufacturing quality and the production efficiency are improved.

The utility model discloses a roller compacted concrete test block forming device, and belongs to the technical field of concrete detection test auxiliary equipment. The device comprises a rack, a vibration mechanism, a test mold, a lifting driving assembly, a bearing plate and a control assembly, the vibration mechanism is arranged on the rack, the test mold is arranged on the vibration mechanism, the lifting driving assembly is arranged on the rack, the bearing plate is connected with the lower end of the lifting driving assembly through a pressure detection assembly and located above the test mold, and the control assembly is arranged on the rack. The control assembly is arranged on the rack and electrically connected with the pressure detection assembly and the lifting driving assembly. The device can automatically control the pressure bearing plate to apply pressure intensity of 4.9 Kpa to the surface of roller compacted concrete and keep the pressure intensity, the manufacturing quality of roller compacted concrete test blocks is ensured, the automation degree is high, operation and use are convenient, and the labor intensity is remarkably reduced.

The present application relates to a kind of asymmetric chord of steel truss beam welding and manufacturing method, comprising the following steps:1, bottom plate, web, node plate and diaphragm assembly and welding;2, assembly and welding node plate box outside short joint web one;3, assembly and symmetric welding top plate;4, first time overturning again weld top plate in box body interior weld;5, assembly and weld web short joint component;6, second time overturning last weld top plate in box body exterior weld.The advantages of the welding method process are as follows:1, by optimizing the welding process of each structural member of chord, and adjusting the welding direction of individual structural member, so that each weld has better operating space, reduces the heat input of each weld, thereby ensuring the manufacturing quality of the entire chord;2, reasonable planning the welding sequence of each structural member, so that the post-welding deformation stress of each part of the manufactured chord tends to be balanced, which can reduce post-welding correction, improve manufacturing precision and reduce manufacturing cost.

The utility model discloses an air bearing type plate shape detection roller structure, and belongs to the technical field of thin plate strip quality detection equipment. The two ends of a mandrel of the mandrel structure unit are connected to the supporting frame unit, and a roller ring of the roller ring structure unit is arranged on the mandrel in a sleeving mode. According to the utility model, an air bearing type flexible structure is adopted, so that scratches caused by friction between the soft-state thin strip plate and the roll collar are greatly reduced, and the detection and manufacturing quality of the soft-state thin strip plate is improved; the device is simple in design structure, fast to install, firm, durable, sensitive in signal feedback and convenient to maintain and overhaul, the optimal weight distribution is realized, the gravity center is lowered, and the detection stability is improved; the air bearing type strip shape detection roller adopts the air pressure sensor to feed back the spatial variation of pure gas, can quickly feed back the surface quality of a thin strip by utilizing the flowing sensitivity characteristic of the gas, and effectively improves the quick and automatic intervention capability on the surface quality of a thin strip plate.